automated video transcription and summarisation
The proposed system takes a YouTube video URL as input and utilizes the YouTube Transcript API to extract the spoken content of the video in textual format. This raw transcript is then processed through two distinct summarization methodologies. The first approach is based on Natural Language Toolkit (NLTK), implementing an extractive summarization model that selects significant sentences from the transcript based on statistical and linguistic features. The second approach employs Transformer-based models from Hugging Face, leveraging deep learning for abstractive summarization, which rewrites the content in a more coherent and human-like manner.